© 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. 97446
    Prev
    Next
    INDEX
    Explanations

    The

    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
     	↵
    -0.08
    	the
    -0.08
     atawa
    -0.08
    The
    -0.08
     首
    -0.08
     bedrag
    -0.08
     kere
    -0.08
     tarda
    -0.08
     mü
    -0.08
     The
    -0.07
    POSITIVE LOGITS
    obal
    0.08
    ater
    0.08
    elijks
    0.08
    _LINES
    0.07
    kla
    0.07
    atro
    0.07
    med
    0.07
    _RANGE
    0.07
    _LINE
    0.07
    kos
    0.07
    Activations Density 0.002%

    No Known Activations