© 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. 11-RESID-POST-AA
    11. 65584
    Prev
    Next
    INDEX
    Explanations

    UR robots

    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
     persona
    -0.09
     seção
    -0.08
     অধ
    -0.08
     Persona
    -0.08
     inglês
    -0.07
     majd
    -0.07
     compens
    -0.07
     retained
    -0.07
     Italiano
    -0.07
     retaining
    -0.07
    POSITIVE LOGITS
    すると
    0.07
    џ
    0.07
    ませ
    0.07
    ити
    0.07
    ません
    0.07
    Village
    0.07
     faibles
    0.07
    �
    0.07
     കൊണ്ട
    0.07
    _layers
    0.07
    Activations Density 0.000%

    No Known Activations