© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103503
    Prev
    Next
    INDEX
    Explanations

    identity

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     identities
    -0.11
    ॉर्ड
    -0.09
     identidade
    -0.09
     identité
    -0.09
     identity
    -0.09
    IDENT
    -0.08
    ોર્ડ
    -0.08
     identificação
    -0.08
     garota
    -0.08
    Identity
    -0.08
    POSITIVE LOGITS
     Verification
    0.11
     verification
    0.11
     Provider
    0.10
    Provider
    0.10
    provider
    0.10
    _PROVIDER
    0.10
     защит
    0.10
     Providers
    0.09
     management
    0.09
     protection
    0.09
    Activations Density 0.003%

    No Known Activations