© 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. 5822
    Prev
    Next
    INDEX
    Explanations

    earlier

    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
     initially
    -0.16
     early
    -0.15
     tidligere
    -0.15
    Earlier
    -0.15
     próxim
    -0.15
     Early
    -0.15
     later
    -0.15
     Earlier
    -0.15
     далее
    -0.15
    early
    -0.15
    POSITIVE LOGITS
    -mentioned
    0.18
    -than
    0.13
     than
    0.12
    -stage
    0.12
    -described
    0.12
    -defined
    0.12
    -established
    0.11
    mentioned
    0.11
     থেকেই
    0.11
     నుం�
    0.11
    Activations Density 0.062%

    No Known Activations