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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 102867
    Prev
    Next
    INDEX
    Explanations

    Surrealism

    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
     Simpl
    -0.08
    .amazonaws
    -0.08
    _hi
    -0.08
    .king
    -0.08
    .transpose
    -0.08
     hi
    -0.08
    stdcall
    -0.08
    ащ
    -0.08
     simplify
    -0.07
     Hi
    -0.07
    POSITIVE LOGITS
     kurt
    0.09
     gezamen
    0.09
     fug
    0.09
     camar
    0.08
     bijeenkomst
    0.08
     poets
    0.08
     persecut
    0.08
     comrades
    0.08
     باريس
    0.08
     decad
    0.08
    Activations Density 0.011%

    No Known Activations