© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47652
    Prev
    Next
    INDEX
    Explanations

    Indus Valley civilization

    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
     X
    -0.10
    	X
    -0.08
    <X
    -0.08
     ministre
    -0.08
     xog
    -0.07
     реж
    -0.07
    =X
    -0.07
     Xunit
    -0.07
    	x
    -0.07
    **)(&
    -0.07
    POSITIVE LOGITS
    _SS
    0.09
    _RING
    0.09
    Ro
    0.08
     Ravi
    0.08
    RI
    0.08
    Ri
    0.08
    cciones
    0.08
    RC
    0.08
    _L
    0.07
    RIO
    0.07
    Activations Density 0.002%

    No Known Activations