Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19035
    Prev
    Next
    INDEX
    Explanations

    inverse functions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totals
    -0.08
     elapsed
    -0.08
    -progress
    -0.08
    落
    -0.08
    _elapsed
    -0.08
    Severity
    -0.08
     divisible
    -0.08
    突出
    -0.07
    udget
    -0.07
    .elapsed
    -0.07
    POSITIVE LOGITS
    inverse
    0.16
     inverse
    0.16
    Inverse
    0.15
    _reverse
    0.15
    reverse
    0.15
     reverse
    0.14
    _inverse
    0.14
    Reverse
    0.14
     reversal
    0.14
     reciprocal
    0.13
    Activations Density 0.023%

    No Known Activations