© 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. 23-RESID-POST-AA
    11. 48151
    Prev
    Next
    INDEX
    Explanations

    Sow

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (C
    -0.08
    チ
    -0.08
    (h
    -0.07
    _strip
    -0.07
     GC
    -0.07
    係
    -0.07
     stunning
    -0.07
    AQ
    -0.07
     HPC
    -0.07
    宗
    -0.07
    POSITIVE LOGITS
    jet
    0.10
    jeto
    0.10
    bull
    0.10
    jets
    0.10
    jale
    0.09
    ohl
    0.09
    iatamente
    0.09
    jeć
    0.09
    jero
    0.09
    baby
    0.09
    Activations Density 0.001%

    No Known Activations