© 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. 127
    Prev
    Next
    INDEX
    Explanations

    CG

    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
    Proto
    -0.09
    ەر
    -0.08
    يفة
    -0.07
    _STATIC
    -0.07
    _PROTO
    -0.07
     upt
    -0.07
    _Abstract
    -0.07
     سعود
    -0.07
    ад
    -0.07
    _proto
    -0.07
    POSITIVE LOGITS
     negotiating
    0.09
     comercio
    0.08
     pratica
    0.08
    -informed
    0.08
    senha
    0.08
     concili
    0.08
     jailbreak
    0.08
    (training
    0.08
     pono
    0.08
     negotiate
    0.08
    Activations Density 0.001%

    No Known Activations