© 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. 47099
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     میڈیا
    -0.08
     پہلے
    -0.08
     doporu
    -0.08
     нагруз
    -0.08
     Añ
    -0.08
     ondernemer
    -0.08
     сниз
    -0.08
     Edmund
    -0.07
    ેચ
    -0.07
    ầy
    -0.07
    POSITIVE LOGITS
    This
    0.08
    joint
    0.08
    Train
    0.07
    (View
    0.07
    neg
    0.07
    call
    0.07
     trains
    0.07
     tyy
    0.07
     */
↵
↵
    0.07
    (vec
    0.07
    Activations Density 0.023%

    No Known Activations