© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8071
    Prev
    Next
    INDEX
    Explanations

    silicone

    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
    :《
    -0.09
     Mozart
    -0.09
     Macbeth
    -0.08
     Animal
    -0.08
    Nap
    -0.08
    aliland
    -0.08
    тера
    -0.08
    qué
    -0.08
    animal
    -0.08
    abilia
    -0.08
    POSITIVE LOGITS
     sinu
    0.08
     oint
    0.08
     DNS
    0.08
     initial
    0.08
     PATCH
    0.07
     स्वीकार
    0.07
    Primitive
    0.07
     sealing
    0.07
     waterproof
    0.07
    _FAILED
    0.07
    Activations Density 0.009%

    No Known Activations