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. 76465
    Prev
    Next
    INDEX
    Explanations

    Punctuation/Agreement Structure

    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
    @end
    -0.08
     beforehand
    -0.08
     الدعم
    -0.08
    .recycler
    -0.08
     ondersteunen
    -0.08
    ెక
    -0.08
    Coeff
    -0.07
     unterstützen
    -0.07
    /repos
    -0.07
    Hasher
    -0.07
    POSITIVE LOGITS
     declaraciones
    0.09
     marijuana
    0.09
     byl
    0.08
     withdrawals
    0.08
     criminal
    0.08
     covenant
    0.07
    bog
    0.07
     complain
    0.07
     alleging
    0.07
    Amenities
    0.07
    Activations Density 0.010%

    No Known Activations