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. 49044
    Prev
    Next
    INDEX
    Explanations

    code, documentation, messages

    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
    Ssl
    -0.08
     pili
    -0.08
    =models
    -0.08
     Pili
    -0.08
    ов
    -0.08
    ുവര
    -0.08
    ẩm
    -0.08
    arlas
    -0.07
     boosts
    -0.07
     slogans
    -0.07
    POSITIVE LOGITS
     escrever
    0.08
     город
    0.08
     gelesen
    0.08
     poem
    0.08
     حل
    0.08
     Temper
    0.08
     solve
    0.07
     Seek
    0.07
     acompan
    0.07
    Temper
    0.07
    Activations Density 0.031%

    No Known Activations