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. 112755
    Prev
    Next
    INDEX
    Explanations

    invitational

    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
     stamps
    -0.08
     warp
    -0.07
     necessity
    -0.07
    imetype
    -0.07
     tổ
    -0.07
     bodem
    -0.07
     attack
    -0.07
     princípio
    -0.07
     stile
    -0.07
     podes
    -0.07
    POSITIVE LOGITS
     Ow
    0.08
     REALTOR
    0.08
     HOA
    0.08
     متابعة
    0.07
     Spar
    0.07
     REALTORS
    0.07
     Mose
    0.07
     monies
    0.07
     TBD
    0.07
     Am
    0.07
    Activations Density 0.002%

    No Known Activations