Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 66010
    Prev
    Next
    INDEX
    Explanations

    rosemary

    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
    vonne
    -0.08
     square
    -0.07
    angible
    -0.07
     drummer
    -0.07
     murderer
    -0.07
    _",
    -0.07
     CREDIT
    -0.07
     sexuelle
    -0.07
     اجتما
    -0.07
    aya
    -0.07
    POSITIVE LOGITS
     petrol
    0.08
    retry
    0.08
     വി�
    0.08
     produc
    0.07
    Fi
    0.07
     rosemary
    0.07
     Productivity
    0.07
    0.07
     Mont
    0.07
    Vid
    0.07
    Activations Density 0.001%

    No Known Activations