© 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. 97220
    Prev
    Next
    INDEX
    Explanations

    say "иб" ending

    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
     giv
    -0.08
    enta
    -0.08
    ెక్టర్
    -0.08
    ством
    -0.08
    打造
    -0.07
    econ
    -0.07
    Nachdem
    -0.07
     sunt
    -0.07
    ächst
    -0.07
    ento
    -0.07
    POSITIVE LOGITS
    ибка
    0.23
    иб
    0.17
    иба
    0.12
    باه
    0.10
    ИБ
    0.10
    ib
    0.09
    иби
    0.09
    ибо
    0.08
    obh
    0.08
    .Validation
    0.08
    Activations Density 0.000%

    No Known Activations