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. 109075
    Prev
    Next
    INDEX
    Explanations

    depends

    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
    വ്
    -0.08
     corpore
    -0.08
    ecn
    -0.07
     widers
    -0.07
    _rev
    -0.07
    407
    -0.07
    Polar
    -0.07
    ाँ
    -0.07
     Санкт
    -0.07
     Konstant
    -0.07
    POSITIVE LOGITS
     tro
    0.08
     Mario
    0.08
     peaked
    0.08
    ,..
    0.07
     inz
    0.07
     productions
    0.07
     Soldiers
    0.07
     riders
    0.07
     Horses
    0.07
     guy
    0.07
    Activations Density 6.058%

    No Known Activations