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. 26800
    Prev
    Next
    INDEX
    Explanations

    code errors

    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
     safegu
    -0.08
    MG
    -0.08
    @Bean
    -0.08
    કાશ
    -0.08
     proj
    -0.07
     shelters
    -0.07
     되어
    -0.07
     blot
    -0.07
    Qc
    -0.07
     longo
    -0.07
    POSITIVE LOGITS
    EINVAL
    0.10
    Invalid
    0.09
    .Invalid
    0.09
     Invalid
    0.09
    .IOException
    0.09
     Illegal
    0.09
    _INVALID
    0.09
     IOException
    0.08
     invalid
    0.08
    Illegal
    0.08
    Activations Density 0.003%

    No Known Activations