© 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. 6137
    Prev
    Next
    INDEX
    Explanations

    say variations of "slope"

    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
    Charsets
    -0.09
     Fiat
    -0.09
    iów
    -0.09
     Hav
    -0.08
     cried
    -0.08
    ార్ట
    -0.08
    ియన్
    -0.08
     바이
    -0.08
     Artemis
    -0.08
     التحقيق
    -0.08
    POSITIVE LOGITS
     slope
    0.35
    Slope
    0.27
     slopes
    0.25
    _s
    0.22
     pente
    0.21
     gradient
    0.21
    -s
    0.21
    �
    0.19
    gradient
    0.19
    	s
    0.19
    Activations Density 0.121%

    No Known Activations