© 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. 48055
    Prev
    Next
    INDEX
    Explanations

    back

    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
    ియ
    -0.08
    重新
    -0.08
    חי
    -0.08
    izados
    -0.08
    853
    -0.08
    uting
    -0.08
     לצד
    -0.08
     מחדש
    -0.08
    _trial
    -0.08
     термин
    -0.07
    POSITIVE LOGITS
    door
    0.13
    /back
    0.13
    (back
    0.13
    /front
    0.13
    track
    0.13
    lash
    0.12
    grond
    0.12
    ups
    0.11
    slash
    0.11
    ward
    0.11
    Activations Density 0.043%

    No Known Activations