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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 100
    Prev
    Next
    INDEX
    Explanations

    Crime and punishment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .cache
    -0.08
     Herkunft
    -0.08
    _CACHE
    -0.08
     Herren
    -0.08
    .Factory
    -0.08
    -produced
    -0.08
    .Master
    -0.08
     produced
    -0.08
    .manager
    -0.08
     Obtain
    -0.08
    POSITIVE LOGITS
     punish
    0.17
     criminal
    0.16
     delitos
    0.16
     punishment
    0.15
     уголов
    0.15
     offenses
    0.15
     penal
    0.14
     punitive
    0.14
     offences
    0.14
     homicide
    0.14
    Activations Density 0.046%

    No Known Activations