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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47844
    Prev
    Next
    INDEX
    Explanations

    minify

    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
     पो
    -0.08
     sixty
    -0.08
     habilidade
    -0.07
     conting
    -0.07
     Governors
    -0.07
     Raised
    -0.07
    Raised
    -0.07
    ্তার
    -0.07
     Portugal
    -0.07
    Begin
    -0.07
    POSITIVE LOGITS
     concat
    0.09
    concat
    0.09
     mfe
    0.08
    tegen
    0.08
     YM
    0.08
     убрать
    0.08
     ثالث
    0.08
    ibox
    0.08
     switch
    0.08
     minim
    0.08
    Activations Density 0.001%

    No Known Activations