© 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. 97320
    Prev
    Next
    INDEX
    Explanations

    Br

    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
    uß
    -0.09
    us
    -0.09
    ay
    -0.09
    un
    -0.08
    unswick
    -0.08
    u
    -0.08
    ut
    -0.08
    abant
    -0.07
    andenburg
    -0.07
    صلاح
    -0.07
    POSITIVE LOGITS
    ings
    0.11
    acket
    0.11
    ains
    0.10
    illiance
    0.10
    ampton
    0.09
    ushing
    0.09
    ackets
    0.08
    ingss
    0.08
    أن
    0.08
    ansom
    0.08
    Activations Density 0.004%

    No Known Activations