© 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. 11-RESID-POST-AA
    11. 54879
    Prev
    Next
    INDEX
    Explanations

    French grammar

    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
    旨
    -0.08
     Battles
    -0.08
     initialization
    -0.07
    _initializer
    -0.07
    �
    -0.07
    oret
    -0.07
     Lom
    -0.07
    endig
    -0.07
     spro
    -0.07
    感染
    -0.07
    POSITIVE LOGITS
     guint
    0.09
    .study
    0.09
     നല്
    0.08
     séance
    0.08
    .ide
    0.08
    atenate
    0.08
     lākou
    0.08
    atly
    0.08
     كبير
    0.08
     તથા
    0.07
    Activations Density 0.000%

    No Known Activations