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. 113798
    Prev
    Next
    INDEX
    Explanations

    exercise instructions

    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
    394
    -0.08
     COPYING
    -0.07
     судь
    -0.07
     Passing
    -0.07
     IOException
    -0.07
     teht
    -0.07
     деле
    -0.07
     Figure
    -0.07
    ulnerability
    -0.07
    .permission
    -0.07
    POSITIVE LOGITS
     antib
    0.09
     annonser
    0.09
    Smooth
    0.09
    Digite
    0.09
    Soll
    0.08
     antagonist
    0.08
    గా
    0.08
    Seleccione
    0.08
    ابية
    0.08
     enfat
    0.08
    Activations Density 0.010%

    No Known Activations