© 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. 48655
    Prev
    Next
    INDEX
    Explanations

    af

    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
    nders
    -0.08
    iner
    -0.07
     Gl
    -0.07
     Anti
    -0.07
    ky
    -0.07
     rejet
    -0.07
    teur
    -0.07
    -0.07
    inerja
    -0.07
    pository
    -0.07
    POSITIVE LOGITS
    нан
    0.11
     civilized
    0.08
    .with
    0.08
    àng
    0.08
    ੇ
    0.08
     вар
    0.08
    дың
    0.08
    刘
    0.08
     möjlig
    0.07
     hoặc
    0.07
    Activations Density 0.000%
    No Known Activations