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. 43079
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     фіз
    -0.08
     contiguous
    -0.08
    产生
    -0.08
    期间
    -0.07
     deja
    -0.07
     indiv
    -0.07
     factual
    -0.07
     compressed
    -0.07
     physical
    -0.07
     മുഴ
    -0.07
    POSITIVE LOGITS
     safeguards
    0.16
     safeguard
    0.15
     guards
    0.13
     safeguarding
    0.13
     guarding
    0.12
     Checks
    0.12
     Guards
    0.12
     precautions
    0.11
     Defensive
    0.11
     safegu
    0.11
    Activations Density 0.031%

    No Known Activations