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. 55858
    Prev
    Next
    INDEX
    Explanations

    Data recovery software

    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
     informing
    -0.09
     {}".
    -0.09
     Cannon
    -0.08
     occasionally
    -0.08
     suffis
    -0.08
     friv
    -0.08
    Inform
    -0.07
     :)↵
    -0.07
     inaan
    -0.07
    Optional
    -0.07
    POSITIVE LOGITS
     verlor
    0.09
     defective
    0.09
     العناصر
    0.09
     desapar
    0.09
    _deleted
    0.08
     വിവാഹ
    0.08
    0.08
    类
    0.08
    ghar
    0.08
     autént
    0.08
    Activations Density 0.026%

    No Known Activations