© 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. 19-RESID-POST-AA
    11. 102733
    Prev
    Next
    INDEX
    Explanations

    need

    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
     their
    -0.10
     waahi
    -0.09
     both
    -0.09
    elaar
    -0.09
    iculos
    -0.09
     hankali
    -0.09
    HING
    -0.09
     hanyar
    -0.08
    igingen
    -0.08
     actual
    -0.08
    POSITIVE LOGITS
     Showing
    0.12
    证明
    0.11
     showing
    0.11
    Showing
    0.10
     proving
    0.10
     Show
    0.10
    -show
    0.10
    証
    0.10
     zeigen
    0.10
     demostrar
    0.10
    Activations Density 0.023%

    No Known Activations