© 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. 5800
    Prev
    Next
    INDEX
    Explanations

    Erdos–Ko–Rado theorem

    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
    发布
    -0.09
    ublish
    -0.08
     published
    -0.07
     released
    -0.07
    (In
    -0.07
    released
    -0.07
    Published
    -0.07
    .publish
    -0.07
     Tast
    -0.07
     发布
    -0.07
    POSITIVE LOGITS
     Ko
    0.10
    Ko
    0.10
    -ko
    0.09
     ko
    0.09
    ko
    0.09
     lov
    0.09
     adhesives
    0.09
     wassen
    0.08
    ’activ
    0.08
     ranar
    0.08
    Activations Density 0.000%

    No Known Activations