© 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. 94983
    Prev
    Next
    INDEX
    Explanations

    simplex noise and x

    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
     waar
    -0.09
     aa
    -0.07
     ман
    -0.07
    094
    -0.07
     ancora
    -0.07
     certes
    -0.06
    VE
    -0.06
    _FUNC
    -0.06
     monthly
    -0.06
    _interfaces
    -0.06
    POSITIVE LOGITS
    odend
    0.09
     chemistry
    0.08
     départ
    0.08
     Packing
    0.08
    ίζουν
    0.08
    artement
    0.08
     bisnis
    0.08
    -pad
    0.08
    гер
    0.07
     fyl
    0.07
    Activations Density 0.001%

    No Known Activations