© 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. 97345
    Prev
    Next
    INDEX
    Explanations

    say "anges"

    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
    arrollo
    -0.09
    esion
    -0.09
    well
    -0.09
    arroll
    -0.08
     Federation
    -0.08
    clerosis
    -0.08
    ion
    -0.08
     well
    -0.08
    OLAR
    -0.07
    y
    -0.07
    POSITIVE LOGITS
    anges
    0.13
    naments
    0.11
    tho
    0.10
    tschaft
    0.10
    ANGES
    0.09
    anged
    0.09
    çamento
    0.09
    typ
    0.09
    thon
    0.09
    angep
    0.08
    Activations Density 0.002%

    No Known Activations