© 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. 23-RESID-POST-AA
    11. 97440
    Prev
    Next
    INDEX
    Explanations

    Rain and downpours

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bri
    -0.08
     leyi
    -0.07
    .c
    -0.07
     chỉ
    -0.07
     going
    -0.07
     C
    -0.07
     ;↵
    -0.07
     menc
    -0.07
     dehydr
    -0.07
     s
    -0.07
    POSITIVE LOGITS
    0.08
     Shrine
    0.08
    ombra
    0.08
     despacho
    0.08
    уса
    0.07
    554
    0.07
     assess
    0.07
    lger
    0.07
    prete
    0.07
    umaa
    0.07
    Activations Density 0.001%
    No Known Activations