© 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. 96737
    Prev
    Next
    INDEX
    Explanations

    say variations of "stand"

    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
    orso
    -0.09
    ਲ
    -0.08
     põhj
    -0.08
    Latency
    -0.07
     escalate
    -0.07
    -Line
    -0.07
     LPARAM
    -0.07
    abela
    -0.07
    orial
    -0.07
    ੋਰ
    -0.07
    POSITIVE LOGITS
    standing
    0.25
    stand
    0.24
    stands
    0.20
    stood
    0.17
     Stand
    0.17
    standig
    0.17
     standing
    0.17
    Stand
    0.17
     stand
    0.16
    stånd
    0.16
    Activations Density 0.001%

    No Known Activations