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. 43511
    Prev
    Next
    INDEX
    Explanations

    Tapping/clicking

    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
     każ
    -0.08
     فائد
    -0.08
     mereka
    -0.08
     lợi
    -0.08
    百分
    -0.08
     keuntungan
    -0.08
     crowded
    -0.08
    ٹل
    -0.08
     antibody
    -0.08
     afscheid
    -0.07
    POSITIVE LOGITS
     hacker
    0.10
     secr
    0.09
    Secrets
    0.09
     hidden
    0.09
     togg
    0.09
     parano
    0.09
     hack
    0.09
     contraseña
    0.09
     Secrets
    0.09
     bug
    0.08
    Activations Density 0.009%

    No Known Activations