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. 44992
    Prev
    Next
    INDEX
    Explanations

    Alloys and weight

    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
     segons
    -0.10
     Senhor
    -0.09
     righteous
    -0.09
     psychic
    -0.09
     consecutive
    -0.09
     assust
    -0.08
     successive
    -0.08
     Terminal
    -0.08
     ordained
    -0.08
     连
    -0.08
    POSITIVE LOGITS
     aerospace
    0.10
     विमान
    0.09
     fus
    0.09
     aircraft
    0.09
     vorne
    0.08
     corrosion
    0.08
     हल
    0.08
     Aerospace
    0.08
    Aircraft
    0.08
     hull
    0.08
    Activations Density 0.010%

    No Known Activations