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. 117540
    Prev
    Next
    INDEX
    Explanations

    newlines/formatting

    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
     Regular
    -0.08
     Exactly
    -0.08
     exactly
    -0.07
     sent
    -0.07
     regular
    -0.07
    regular
    -0.07
    ffa
    -0.07
     havoc
    -0.07
    Regular
    -0.07
     RTV
    -0.07
    POSITIVE LOGITS
    ależ
    0.09
    Resultados
    0.09
     hábito
    0.09
     предпочт
    0.08
    аліся
    0.08
    awan
    0.08
    Listado
    0.08
    ано
    0.08
     bebê
    0.08
    Australian
    0.08
    Activations Density 0.005%

    No Known Activations