© 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. 11-RESID-POST-AA
    11. 129301
    Prev
    Next
    INDEX
    Explanations

    resemblance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    íts
    -0.08
    (di
    -0.08
    _guard
    -0.08
    di
    -0.08
    _DI
    -0.08
    _di
    -0.08
     quella
    -0.08
    ең
    -0.08
    SU
    -0.08
    .di
    -0.07
    POSITIVE LOGITS
    giu
    0.08
     الاجتماعية
    0.08
     lawmakers
    0.08
    ುತ
    0.08
    -haspopup
    0.08
     sporty
    0.08
     Kreis
    0.08
     Mile
    0.07
     Parlamento
    0.07
    Coeff
    0.07
    Activations Density 0.000%

    No Known Activations