Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112126
    Prev
    Next
    INDEX
    Explanations

    trape

    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
     Jair
    -0.09
    FORE
    -0.08
     અવ
    -0.08
     jag
    -0.08
    rf
    -0.07
     भ
    -0.07
     मानव
    -0.07
    \Entity
    -0.07
    jería
    -0.07
     Bef
    -0.07
    POSITIVE LOGITS
     UT
    0.08
    /non
    0.08
     UU
    0.08
     UB
    0.08
    ¦
    0.08
    性质
    0.07
    (separator
    0.07
    .separator
    0.07
     Catalunya
    0.07
     Simpson
    0.07
    Activations Density 0.004%

    No Known Activations