© 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. 29507
    Prev
    Next
    INDEX
    Explanations

    Descriptive words

    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
     Ford
    -0.09
    Ford
    -0.09
     Cite
    -0.08
     Justicia
    -0.08
    ukan
    -0.08
     ث
    -0.08
    亚
    -0.08
    Mx
    -0.08
     cite
    -0.07
    _ep
    -0.07
    POSITIVE LOGITS
     pervasive
    0.08
    -साथ
    0.08
    ambul
    0.07
     disso
    0.07
     integrante
    0.07
    。また
    0.07
     therein
    0.07
     darauf
    0.07
    Uw
    0.07
     चिं
    0.07
    Activations Density 0.110%

    No Known Activations