© 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. 96734
    Prev
    Next
    INDEX
    Explanations

    Sp

    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
    in
    -0.08
    hq
    -0.08
    rides
    -0.08
    engwa
    -0.08
    hman
    -0.07
    eri
    -0.07
    arım
    -0.07
    rada
    -0.07
    FIN
    -0.07
    hid
    -0.07
    POSITIVE LOGITS
    ouse
    0.11
     სპ
    0.10
     Sp
    0.10
    ool
    0.10
    anning
    0.10
    ending
    0.10
    .Sp
    0.10
     സ്പ
    0.10
     સ્પ
    0.10
    rawd
    0.09
    Activations Density 0.008%

    No Known Activations