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. 103195
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ök
    -0.09
    inom
    -0.08
    BIO
    -0.08
    Unnamed
    -0.07
    BI
    -0.07
     justement
    -0.07
    _DIG
    -0.07
    ,所以
    -0.07
    现在
    -0.07
     DIG
    -0.07
    POSITIVE LOGITS
    永久
    0.08
     cheers
    0.08
     lev
    0.08
     खोल
    0.08
     voila
    0.07
     móviles
    0.07
     Комп
    0.07
     Vintage
    0.07
     samenleving
    0.07
    771
    0.07
    Activations Density 0.045%

    No Known Activations