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. 90102
    Prev
    Next
    INDEX
    Explanations

    punctuation/code

    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
     Gale
    -0.08
    Κα
    -0.08
    _DUP
    -0.08
    سبة
    -0.08
    붙
    -0.07
    כל
    -0.07
     incurs
    -0.07
    قس
    -0.07
    -au
    -0.07
     Null
    -0.07
    POSITIVE LOGITS
     minlength
    0.09
     uzun
    0.09
    -length
    0.08
     lenght
    0.08
     लंब
    0.08
    长度
    0.08
     երկար
    0.08
     kriter
    0.08
    Length
    0.08
     खेल
    0.08
    Activations Density 0.002%

    No Known Activations