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. 109206
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    Synopsis
    -0.09
     лод
    -0.08
    لاص
    -0.08
    πό
    -0.08
    .pg
    -0.08
    avoidable
    -0.08
     wire
    -0.08
     cynical
    -0.08
    ποί
    -0.07
     παί
    -0.07
    POSITIVE LOGITS
     Karl
    0.10
     Гар
    0.08
     Rapport
    0.08
    Karl
    0.08
    zuje
    0.08
    REF
    0.08
     Din
    0.08
     Rein
    0.08
     unset
    0.08
     Empire
    0.08
    Activations Density 0.002%

    No Known Activations