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. 23289
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    .sulake
    -0.08
     EEG
    -0.08
     chimp
    -0.08
     poudre
    -0.08
    usionsoft
    -0.08
     Syndrome
    -0.08
     Zodiac
    -0.08
     MOST
    -0.08
     Berd
    -0.07
     Siam
    -0.07
    POSITIVE LOGITS
    @Enable
    0.09
    .Asp
    0.09
     कोविड
    0.08
    Grpc
    0.08
     existential
    0.08
    中国特色社会主义
    0.08
    Docker
    0.08
    开放
    0.08
    .NET
    0.08
    _actor
    0.08
    Activations Density 0.012%

    No Known Activations