© 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. 3-RESID-POST-AA
    11. 1458
    Prev
    Next
    INDEX
    Explanations

    trick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    غام
    -0.08
     bv
    -0.08
     sensibles
    -0.07
    mäßig
    -0.07
    Derived
    -0.07
    dda
    -0.07
    માં
    -0.07
    ofs
    -0.07
     માં
    -0.07
     volts
    -0.07
    POSITIVE LOGITS
     hiel
    0.09
     chacune
    0.09
    ije
    0.08
     lunches
    0.07
     wykony
    0.07
     lunch
    0.07
    enemy
    0.07
     emp
    0.07
     عمليات
    0.07
     chacun
    0.07
    Activations Density 0.000%

    No Known Activations