© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1454
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     এখ
    -0.08
    cit
    -0.08
    ucht
    -0.08
    Cit
    -0.08
    anjut
    -0.08
     confuse
    -0.08
    Implemented
    -0.08
    aud
    -0.07
     Shq
    -0.07
     وه
    -0.07
    POSITIVE LOGITS
    738
    0.08
     transit
    0.08
     Berg
    0.08
    723
    0.08
    �
    0.07
     quotas
    0.07
    816
    0.07
    parcel
    0.07
     relatief
    0.07
     webpack
    0.07
    Activations Density 0.000%

    No Known Activations