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. 11567
    Prev
    Next
    INDEX
    Explanations

    gen

    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
     बैठक
    -0.08
     delim
    -0.08
     Ether
    -0.08
    bells
    -0.08
     Ut
    -0.08
     সভ
    -0.08
     Formats
    -0.08
     Intens
    -0.07
     Devi
    -0.07
    ry
    -0.07
    POSITIVE LOGITS
     hippoc
    0.09
     basal
    0.09
     anxiety
    0.08
     anemia
    0.08
     geld
    0.08
     antidepress
    0.07
     régions
    0.07
     anx
    0.07
     offspring
    0.07
    anka
    0.07
    Activations Density 0.002%

    No Known Activations