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. 11-RESID-POST-AA
    6. 88281
    Prev
    Next
    INDEX
    Explanations

    laws

    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
     präsentieren
    -0.08
    Nós
    -0.08
     Nós
    -0.08
     Wien
    -0.08
    IZ
    -0.08
     нут
    -0.08
     노
    -0.08
    -produced
    -0.08
    -opacity
    -0.08
     छन
    -0.08
    POSITIVE LOGITS
     offenses
    0.18
    犯罪
    0.17
     crimes
    0.17
     criminal
    0.16
     punish
    0.16
     delitos
    0.15
    罪
    0.15
     felony
    0.15
     offences
    0.15
     prosecut
    0.14
    Activations Density 0.108%

    No Known Activations