© 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. 11-RESID-POST-AA
    11. 68214
    Prev
    Next
    INDEX
    Explanations

    russian

    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
    'ng
    -0.08
     behulp
    -0.08
     breadth
    -0.08
     tots
    -0.08
     capacitor
    -0.08
     reh
    -0.08
     ancho
    -0.07
     ക്യ
    -0.07
     devote
    -0.07
    kich
    -0.07
    POSITIVE LOGITS
     thrown
    0.15
    Thrown
    0.14
    .throw
    0.13
     throwing
    0.12
    throw
    0.12
     NSError
    0.12
     Throw
    0.12
     IOException
    0.12
    .exceptions
    0.12
    	throw
    0.12
    Activations Density 0.011%

    No Known Activations