© 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. 47992
    Prev
    Next
    INDEX
    Explanations

    zm

    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
     যেমন
    -0.08
     forme
    -0.07
     revealed
    -0.07
    iq
    -0.07
     ancestral
    -0.07
    pace
    -0.07
    post
    -0.07
    be
    -0.07
     wur
    -0.07
    lict
    -0.06
    POSITIVE LOGITS
    ienia
    0.16
    niejs
    0.11
    ieni
    0.10
    ien
    0.10
     gode
    0.09
     Grab
    0.09
    	us
    0.09
    ieros
    0.08
    atiiv
    0.08
    ūs
    0.08
    Activations Density 0.000%

    No Known Activations