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. 117564
    Prev
    Next
    INDEX
    Explanations

    a

    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
     mw
    -0.09
     morar
    -0.08
     MW
    -0.08
     sik
    -0.08
    illère
    -0.08
     CW
    -0.08
     MR
    -0.08
     milag
    -0.08
     Castillo
    -0.08
     нер
    -0.07
    POSITIVE LOGITS
     remarkably
    0.09
    丰富
    0.09
     fascinating
    0.09
    非常
    0.08
    Helvetica
    0.08
    十分
    0.08
     весьма
    0.08
     довольно
    0.08
     contem
    0.08
    艳
    0.08
    Activations Density 0.070%

    No Known Activations