© 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. 48461
    Prev
    Next
    INDEX
    Explanations

    kn

    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
    sets
    -0.10
    gled
    -0.09
    brot
    -0.09
    ್ರಮ
    -0.09
    ্রম
    -0.08
    wheel
    -0.08
    tsioon
    -0.08
     immersion
    -0.08
    սկ
    -0.08
    ólicas
    -0.08
    POSITIVE LOGITS
    uckles
    0.10
     Knock
    0.09
    ocker
    0.09
     knock
    0.09
     knocking
    0.09
    acken
    0.09
     knocks
    0.09
    Kn
    0.08
    acker
    0.08
    unks
    0.08
    Activations Density 0.001%

    No Known Activations