Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76120
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
     Neu
    -0.09
     Hold
    -0.08
     lena
    -0.08
     లేద
    -0.07
     Housewives
    -0.07
    Hold
    -0.07
    Neu
    -0.07
     Krishna
    -0.07
     Adding
    -0.07
     Yee
    -0.07
    POSITIVE LOGITS
    -made
    0.10
     tərəfindən
    0.09
    -produced
    0.09
    -designed
    0.09
    *innen
    0.08
     recombinant
    0.08
     zuges
    0.08
     തല
    0.08
    аралық
    0.08
    ാര
    0.08
    Activations Density 0.015%

    No Known Activations