© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113217
    Prev
    Next
    INDEX
    Explanations

    self-harm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     experimenting
    -0.09
     эксперимент
    -0.09
     Experiment
    -0.08
     experimentation
    -0.08
     experiment
    -0.08
     Fay
    -0.08
     Comércio
    -0.08
    Fis
    -0.08
    experiment
    -0.07
    chester
    -0.07
    POSITIVE LOGITS
     advising
    0.12
     discourage
    0.12
     advise
    0.11
     सलाह
    0.10
     encouragement
    0.10
     encourage
    0.10
     advies
    0.10
     hotline
    0.10
     Encourage
    0.10
     urging
    0.10
    Activations Density 0.044%

    No Known Activations