© 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. 103119
    Prev
    Next
    INDEX
    Explanations

    asterisk symbol

    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
     વિગતો
    -0.08
     üzere
    -0.08
     kuulu
    -0.08
    BUFF
    -0.08
     dispara
    -0.08
     gebeurde
    -0.08
    ંતુ
    -0.07
    Total
    -0.07
    كاته
    -0.07
    ונגען
    -0.07
    POSITIVE LOGITS
    *a
    0.09
    *this
    0.09
    Coeff
    0.09
     निजी
    0.08
     coeff
    0.08
    *self
    0.08
    aidh
    0.08
     이를
    0.08
    材
    0.08
    coeff
    0.08
    Activations Density 0.004%

    No Known Activations