© 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. 97277
    Prev
    Next
    INDEX
    Explanations

    Premium

    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
     kh
    -0.08
    TMP
    -0.07
     quanto
    -0.07
    anto
    -0.07
    дөр
    -0.07
     polém
    -0.07
    悟
    -0.07
    콩
    -0.07
     antagonist
    -0.07
    orrelation
    -0.07
    POSITIVE LOGITS
    리
    0.08
    ilie
    0.08
    enced
    0.08
    άλ
    0.08
     Hyper
    0.08
     Porsche
    0.08
    .hyper
    0.08
     Veröffentlichung
    0.08
    ény
    0.07
    enciar
    0.07
    Activations Density 0.000%

    No Known Activations