© 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. 113694
    Prev
    Next
    INDEX
    Explanations

    descriptive, evocative adjectives

    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
     Ç
    -0.09
     CST
    -0.08
     hod
    -0.08
    któ
    -0.08
     CYP
    -0.07
     plante
    -0.07
     bilm
    -0.07
    인은
    -0.07
     يقوم
    -0.07
    hod
    -0.07
    POSITIVE LOGITS
    iveness
    0.08
    欲
    0.08
    753
    0.08
     possibilities
    0.08
    (signature
    0.08
    ensa
    0.08
     outlook
    0.08
     applicability
    0.08
     بودن
    0.07
    _signature
    0.07
    Activations Density 0.074%

    No Known Activations