© 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. 78312
    Prev
    Next
    INDEX
    Explanations

    objects sticking together

    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
     રાહ
    -0.08
    ayaran
    -0.08
    ました
    -0.08
     convi
    -0.08
     relieved
    -0.08
    ahlt
    -0.08
    لیل
    -0.08
    large
    -0.08
     오른
    -0.08
     Nederlandse
    -0.08
    POSITIVE LOGITS
     Hang
    0.08
     To
    0.07
     gloria
    0.07
    To
    0.07
     Great
    0.07
    graphic
    0.06
     Pick
    0.06
    ðan
    0.06
     Laos
    0.06
     graphs
    0.06
    Activations Density 0.000%

    No Known Activations