© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 182
    Prev
    Next
    INDEX
    Explanations

    -

    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
     russian
    -0.09
     joindre
    -0.08
     rubber
    -0.08
    ผู้
    -0.07
     Jo
    -0.07
     chines
    -0.07
     Roll
    -0.07
     hil
    -0.07
     dependent
    -0.07
    -0.07
    POSITIVE LOGITS
     boasting
    0.10
    _UNLOCK
    0.09
    _PHY
    0.08
    ਣਾ
    0.08
    ence
    0.08
     emocion
    0.08
    脸
    0.08
     tenga
    0.08
    .atomic
    0.08
    ాలను
    0.08
    Activations Density 0.001%
    No Known Activations