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. 58795
    Prev
    Next
    INDEX
    Explanations

    contract penalties

    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
    'ebe
    -0.08
    ivirus
    -0.08
     JADX
    -0.08
    bito
    -0.08
     GLenum
    -0.08
    ndi
    -0.08
     Enumeration
    -0.07
    (filename
    -0.07
    Enumeration
    -0.07
    ministr
    -0.07
    POSITIVE LOGITS
     penalties
    0.12
     penal
    0.10
    Penalty
    0.10
     penalty
    0.10
     Penal
    0.09
    罚
    0.09
     stiff
    0.09
     stiffness
    0.09
     mismatch
    0.09
    违
    0.09
    Activations Density 0.009%

    No Known Activations