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. 112781
    Prev
    Next
    INDEX
    Explanations

    plain

    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
     erhöht
    -0.09
     آسان
    -0.08
    追
    -0.08
     выяс
    -0.08
     한번
    -0.08
     батар
    -0.08
     standardized
    -0.08
     berücksichtigt
    -0.08
    نے
    -0.07
     investor
    -0.07
    POSITIVE LOGITS
     mese
    0.08
    annu
    0.08
     Indones
    0.08
    ’ess
    0.08
    luc
    0.08
     fluff
    0.08
     Lett
    0.07
     impedit
    0.07
     fucked
    0.07
    yo
    0.07
    Activations Density 0.012%

    No Known Activations