© 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. 6126
    Prev
    Next
    INDEX
    Explanations

    metá

    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
    dadh
    -0.09
    aughter
    -0.09
    BBC
    -0.08
    ló
    -0.08
    rades
    -0.08
    cmd
    -0.08
    ambres
    -0.08
    sensor
    -0.07
    asas
    -0.07
     Primer
    -0.07
    POSITIVE LOGITS
    trica
    0.11
    quina
    0.10
    quisa
    0.09
    fora
    0.09
     Qua
    0.09
    ivanje
    0.09
    -qu
    0.08
    quo
    0.08
    Qua
    0.08
    oinen
    0.08
    Activations Density 0.001%

    No Known Activations