© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48685
    Prev
    Next
    INDEX
    Explanations

    say "ander" word

    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
    atur
    -0.09
    irties
    -0.09
     tyranny
    -0.08
    ereal
    -0.08
    inerit
    -0.08
    estruct
    -0.08
    ಿಂತ
    -0.08
     بح
    -0.08
     стан
    -0.08
    ater
    -0.07
    POSITIVE LOGITS
    andering
    0.13
    anders
    0.11
    ander
    0.11
    _phrase
    0.08
    離
    0.08
    0.08
    待
    0.08
    wl
    0.08
    owi
    0.07
    ēji
    0.07
    Activations Density 0.001%

    No Known Activations