© 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. 26485
    Prev
    Next
    INDEX
    Explanations

    consideration, decision

    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
     Cosm
    -0.08
    .Exceptions
    -0.07
    -All
    -0.07
     Clifford
    -0.07
     inaccur
    -0.07
    ENDIF
    -0.07
    Trig
    -0.07
     Mish
    -0.07
     improvis
    -0.07
     adh
    -0.07
    POSITIVE LOGITS
    GM
    0.10
    GX
    0.09
     downloads
    0.09
     descargar
    0.08
     referral
    0.08
     GB
    0.08
     download
    0.08
     GM
    0.08
     डाउनलोड
    0.08
    Downloading
    0.08
    Activations Density 0.005%

    No Known Activations