© 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. 97463
    Prev
    Next
    INDEX
    Explanations

    say straight/right

    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
     selon
    -0.10
     posteriormente
    -0.10
    .;
    -0.09
     이후
    -0.09
    .when
    -0.09
     según
    -0.09
     após
    -0.09
     afar
    -0.09
    ;<
    -0.09
    ;,
    -0.09
    POSITIVE LOGITS
     right
    0.29
    right
    0.24
     Right
    0.24
    	right
    0.23
     RIGHT
    0.22
    Right
    0.22
     straight
    0.20
    (right
    0.19
    _right
    0.19
     прямо
    0.19
    Activations Density 0.092%

    No Known Activations