© 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. 6203
    Prev
    Next
    INDEX
    Explanations

    scoring runs

    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
    	process
    -0.13
     process
    -0.12
     Process
    -0.12
    Process
    -0.12
     proceso
    -0.12
     proses
    -0.12
     proseso
    -0.12
     Processo
    -0.12
     Prozess
    -0.12
     processo
    -0.11
    POSITIVE LOGITS
     scored
    0.19
     runs
    0.17
     scoring
    0.16
     పరుగ
    0.16
    _runs
    0.16
    Runs
    0.15
     score
    0.15
     scores
    0.15
    score
    0.15
     Runs
    0.15
    Activations Density 0.020%

    No Known Activations